α-Former: Local-Feature-Aware (L-FA) Transformer

Zhi Xu, Bin Sun, Yue Bai, Yun Fu

Keywords: Camouflaged instance segmentation

Abstract: Despite the success of current segmentation models powered by the transformer, the camouflaged instance segmentation (CIS) task remains a challenge due to the similarity between the target and the background. To address this issue, we propose a novel approach called the local-feature-aware transformer ($\alpha$-Former), inspired by how humans find the camouflaged instance in a given photograph. We use traditional computer vision descriptors to simulate how humans find the unnatural boundary in a given photograph. Then, the information extracted by traditional descriptors can be employed as prior knowledge to enhance the neural network's performance. Moreover, due to the non-learnable characteristics of traditional descriptors, we designed a learnable binary filter to simulate the traditional descriptors. In order to aggregate the information from the backbone and binary filter, we introduce an adapter to merge local features into the transformer framework. Additionally, we introduce an edge-aware feature fusion module to improve boundary results in the segmentation model. Using the proposed transformer-based encoder-decoder architecture, our $\alpha$-Former surpasses state-of-the-art performance on the COD10K and NC4K datasets.

List Of Authors: Zhi, Xu and Bin, Sun and Yue, Bai and Yun, Fu

Submission Number: 564